© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 246342
    Prev
    Next
    INDEX
    Explanations

    daughter, inheriting, divorce

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     وتش
    0.52
     ___
    0.50
     Optical
    0.48
     تهد
    0.48
     geschaffen
    0.47
     **)
    0.47
     Nonlinear
    0.46
     নেট
    0.46
     erziel
    0.46
     وارد
    0.46
    POSITIVE LOGITS
    daughter
    0.49
    피
    0.46
    염
    0.45
    disease
    0.45
    쉬
    0.45
    대
    0.44
    女兒
    0.44
    suff
    0.43
     inheriting
    0.43
    g
    0.43
    Activations Density 0.001%

    No Known Activations